Detailed analysis of Land Use/Land Cover （LULC） using remote sensing data in complex irrigated basins provides complete profile for better water resource management and planning. Using remote sensing data, this stud...Detailed analysis of Land Use/Land Cover （LULC） using remote sensing data in complex irrigated basins provides complete profile for better water resource management and planning. Using remote sensing data, this study provides detailed land use maps of the Lower Chenab Canal irrigated region of Pakistan from 2005 to 2012 for LULC change detection. Major crop types are demarcated by identifying temporal profiles of NDVI using MODIS 250 m × 250 m spatial resolution data. Wheat and rice are found to be major crops in rabi and kharif seasons, respectively. Accuracy assessment of prepared maps is performed using three dif- ferent techniques： error matrix approach, comparison with ancillary data and with previous study. Producer and user accuracies for each class are calculated along with kappa coeffi- cients （K）. The average overall accuracies for rabi and kharif are 82.83% and 78.21%, re- spectively. Producer and user accuracies for individual class range respectively between 72.5% to 77% and 70.1% to 84.3% for rabi and 76.6% to 90.2% and 72% to 84.7% for kharif. The K values range between 0.66 to 0.77 for rabi with average of 0.73, and from 0.69 to 0.74 with average of 0.71 for kharif. LULC change detection indicates that wheat and rice have less volatility of change in comparison with both rabi and kharif fodders. Transformation be- tween cotton and rice is less common due to their completely different cropping conditions. Results of spatial and temporal LULC distributions and their seasonal variations provide useful insights for establishing realistic LULC scenarios for hydrological studies.展开更多
Remote sensing is one of the tool which is very important for the production of Land use and land cover maps through a process called image classification. For the image classification process to be successfully, seve...Remote sensing is one of the tool which is very important for the production of Land use and land cover maps through a process called image classification. For the image classification process to be successfully, several factors should be considered including availability of quality Landsat imagery and secondary data, a precise classification process and user’s experiences and expertise of the procedures. The objective of this research was to classify and map land-use/land-cover of the study area using remote sensing and Geospatial Information System (GIS) techniques. This research includes two sections (1) Landuse/Landcover (LULC) classification and (2) accuracy assessment. In this study supervised classification was performed using Non Parametric Rule. The major LULC classified were agriculture (65.0%), water body (4.0%), and built up areas (18.3%), mixed forest (5.2%), shrubs (7.0%), and Barren/bare land (0.5%). The study had an overall classification accuracy of 81.7% and kappa coefficient (K) of 0.722. The kappa coefficient is rated as substantial and hence the classified image found to be fit for further research. This study present essential source of information whereby planners and decision makers can use to sustainably plan the environment.展开更多
Challenges in land use and land cover(LULC)include rapid urbanization encroaching on agricultural land,leading to fragmentation and loss of natural habitats.However,the effects of urbanization on LULC of different cro...Challenges in land use and land cover(LULC)include rapid urbanization encroaching on agricultural land,leading to fragmentation and loss of natural habitats.However,the effects of urbanization on LULC of different crop types are less concerned.The study assessed the impacts of LULC changes on agriculture and drought vulnerability in the Aguascalientes region,Mexico,from 1994 to 2024,and predicted the LULC in 2034 using remote sensing data,with the goals of sustainable land management and climate resilience strategies.Despite increasing urbanization and drought,the integration of satellite imagery and machine learning models in LULC analysis has been underutilized in this region.Using Landsat imagery,we assessed crop attributes through indices such as normalized difference vegetation index(NDVI),normalized difference water index(NDWI),normalized difference moisture index(NDMI),and vegetation condition index(VCI),alongside watershed delineation and spectral features.The random forest model was applied to classify LULC,providing insights into both historical and future trends.Results indicated a significant decline in vegetation cover(109.13 km^(2))from 1994 to 2024,accompanied by an increase in built-up land(75.11 km^(2))and bare land(67.13 km^(2)).Projections suggested a further decline in vegetation cover(41.51 km^(2))and continued urban land expansion by 2034.The study found that paddy crops exhibited the highest values,while common bean and maize performed poorly.Drought analysis revealed that mildly dry areas in 2004 became severely dry in 2024,highlighting the increasing vulnerability of agriculture to climate change.The study concludes that sustainable land management,improved water resource practices,and advanced monitoring techniques are essential to mitigate the adverse effects of LULC changes on agricultural productivity and drought resilience in the area.These findings contribute to the understanding of how remote sensing can be effectively used for long-term agricultural planning and environmental sustainability.展开更多
Cloud cover constitutes a major obstacle to land cover classification in the humid tropical regions when using optical remote sensing such as Landsat imagery. The advent of freely available Sentinel-1 C band synthetic...Cloud cover constitutes a major obstacle to land cover classification in the humid tropical regions when using optical remote sensing such as Landsat imagery. The advent of freely available Sentinel-1 C band synthetic aperture radar (SAR) imagery offers new opportunities for land cover classification in frequently cloud covered environments. In this study, we investigated the utility of Sentinel-1 for extracting land use land cover (LULC) information in the coastal low lying strip of Douala, Cameroon when compared with Landsat enhanced thematic mapper (TM). We also assessed the potential of integrating Sentinel-1 and Landsat. The major LULC classes in the region included water, settlement, bare ground, dark mangroves, green mangroves, swampy vegetation, rubber, coastal forest and other vegetation and palms. Textural variables including mean, correlation, contrast and entropy were derived from the Sentinel-1 C band. Various conventional image processing techniques and the support vector machine (SVM) algorithm were applied. Only four land cover classes (settlement, water, mangroves and other vegetation and rubber) could be calibrated and validated using SAR imagery due to speckles. The Sentinel-1 only classification yielded a lower overall classification accuracy (67.65% when compared to all Landsat bands (88.7%)). The integrated Sentinel-1 and Landsat data showed no significant differences in overall accuracy assessment (88.71% and 88.59%, respectively). The three best spectral bands (5, 6, 7) of Landsat imagery yielded the highest overall accuracy assessment (91.96%). in the study. These results demonstrate a lower potential of Sentinel-1 for land cover classification in the Douala estuary when compared with cloud free Landsat images. However, comparable results were obtained when only broad classes were considered.展开更多
Information on Land Use and Land Cover Map(LULCM)is essential for environment and socioeconomic applications.Such maps are generally derived from Multispectral Remote Sensing Images(MRSI)via classification.The classif...Information on Land Use and Land Cover Map(LULCM)is essential for environment and socioeconomic applications.Such maps are generally derived from Multispectral Remote Sensing Images(MRSI)via classification.The classification process can be described as information flow from images to maps through a trained classifier.Characterizing the information flow is essential for understanding the classification mechanism,providing solutions that address such theoretical issues as“what is the maximum number of classes that can be classified from a given MRSI?”and“how much information gain can be obtained?”Consequently,two interesting questions naturally arise,i.e.(i)How can we characterize the information flow?and(ii)What is the mathematical form of the information flow?To answer these two questions,this study first hypothesizes that thermodynamic entropy is the appropriate measure of information for both MRSI and LULCM.This hypothesis is then supported by kinetic-theory-based experiments.Thereafter,upon such an entropy,a generalized Jarzynski equation is formulated to mathematically model the information flow,which contains such parameters as thermodynamic entropy of MRSI,thermodynamic entropy of LULCM,weighted F1-score(classification accuracy),and total number of classes.This generalized Jarzynski equation has been successfully validated by hypothesis-driven experiments where 694 Sentinel-2 images are classified into 10 classes by four classical classifiers.This study provides a way for linking thermodynamic laws and concepts to the characterization and understanding of information flow in land cover classification,opening a new door for constructing domain knowledge.展开更多
Human well-being and livelihoods depend on natural ecosystem services(ESs).Following the increment of population,ESs have been deteriorated over time.Ultimately,land use/land cover(LULC)changes have a profound impact ...Human well-being and livelihoods depend on natural ecosystem services(ESs).Following the increment of population,ESs have been deteriorated over time.Ultimately,land use/land cover(LULC)changes have a profound impact on the change of ecosystem.The primary goal of this study is to determine the impacts of LULC changes on ecosystem service values(ESVs)in the upper Gilgel Abbay watershed,Ethiopia.Changes in LULC types were studied using three Landsat images representing 1986,2003,and 2021.The Landsat images were classified using a supervised image classification technique in Earth Resources Data Analysis System(ERDAS)Imagine 2014.We classified ESs in this study into four categories(including provisioning,regulating,supporting,and cultural services)based on global ES classification scheme.The adjusted ESV coefficient benefit approach was employed to measure the impacts of LULC changes on ESVs.Five LULC types were identified in this study,including cultivated land,forest,shrubland,grassland,and water body.The result revealed that the area of cultivated land accounted for 64.50%,71.50%,and 61.50%of the total area in 1986,2003,and 2021,respectively.The percentage of the total area covered by forest was 9.50%,5.90%,and 14.80%in 1986,2003,and 2021,respectively.Result revealed that the total ESV decreased from 7.42×10^(7) to 6.44×10^(7) USD between 1986 and 2003.This is due to the expansion of cultivated land at the expense of forest and shrubland.However,the total ESV increased from 6.44×10^(7) to 7.76×10^(7) USD during 2003-2021,because of the increment of forest and shrubland.The expansion of cultivated land and the reductions of forest and shrubland reduced most individual ESs during 1986-2003.Nevertheless,the increase in forest and shrubland at the expense of cultivated land enhanced many ESs during 2003-2021.Therefore,the findings suggest that appropriate land use practices should be scaled-up to sustainably maintain ESs.展开更多
Chalet farming,as a specific type of agricultural landscape management,has been established in many European mountain ranges,including the Krkono?e Mountains and the Hruby Jeseník Mountains in Czechia.During the ...Chalet farming,as a specific type of agricultural landscape management,has been established in many European mountain ranges,including the Krkono?e Mountains and the Hruby Jeseník Mountains in Czechia.During the operation of such farming from 16/17th century till 1945,many changes in land use/land cover and landscape at all occurred,which are generally evaluated positively.Turbulent events including political,economic and social changes and the displacement of the German-speaking population associated with them in the mid-20th century rapidly ended this development,causing significant landscape changes,such as the abandonment of agricultural land and succession,afforestation,expansion of the alpine tree line,reduction of diversity.The aim of our study is to evaluate changes of land cover(forests,dwarf pine,grasslands,other areas)from 1936/1946 till 2021,secondary succession and driving forces of change for selected meadow enclaves in the Krkonose Mountains and the Hruby Jeseník Mountains after the decline of mountain chalet farming since the middle of 20th century.We used remote sensing methods(aerial imagery)and field research(dendrochronology and comparative photography)to detect the land use/land cover changes in the selected study areas in the Krkono?e Mountains and the Hruby Jeseník Mountains.We documented the process of the succession,which occurred almost immediately after the end of farming,peaking about 10–20 years later,with an earlier start in the Hruby Jeseník Mountains.The succession led to the significant change of land use/land cover and these processes were similar in both mountain ranges.The largest changes were a decrease in grasslands by 62%–64%and an increase in forest area by 33%–40%for both study areas.The abandonment of land is the main consequence of a crucial political driving forces(displacement of German-speaking population)in the Krkono?e Mountains and the Hruby Jeseník Mountains.展开更多
Optimizing the spatial pattern of carbon sequestration service is essential for advancing regional low-carbon development,accelerating the achievement of the"dual carbon"goals,and promoting the high-quality ...Optimizing the spatial pattern of carbon sequestration service is essential for advancing regional low-carbon development,accelerating the achievement of the"dual carbon"goals,and promoting the high-quality development of ecological environment.The carbon sequestration capacity within the mountain-desert-oasis system(MDOS),a unique landscape pattern,exhibits significant gradient characteristics,and its carbon sink potential can be substantially improved through multi-scale spatial optimization.This study employed the Integrated Valuation of Ecosystem Services and Tradeoff(InVEST)model to estimate carbon storage and sequestration(CSS)in the Gansu section of Heihe River Basin,China,a representative MDOS,based on land use/land cover(LULC)data from 1990 to 2020.The Patch-level Land Use Simulation(PLUS)model was coupled to simulate LULC and estimate carrying CSS under natural development(ND),ecological protection(EP),water constraint(WC),and economic development(ED)scenarios for 2035.Furthermore,the study constructed and optimized the CSS pattern on the basis of economic and ecological benefits,exploring the guiding significance of different scenarios for pattern optimization.The results showed that CSS spatial distribution is closely correlated with LULC pattern,and CSS is expected to improve in the future.CSS showed an overall increase across subsystems during 1990–2020,but varied across LULC types.CSS of construction land in all subsystems exhibited an increasing trend,while CSS of unused land showed a decreasing trend,with specific changes of 1.68×103 and 3.43×105 t,respectively.Regional CSS dynamics were mainly driven by conversions among unused land,cultivated land,and grassland.The CSS pattern of MDOS was divided into carbon sink functional region(CSFR),low carbon conservation region(LCCR),low carbon economic region(LCER),and economic development region(EDR).Water resources coordination served as the basis of pattern optimization,while the four dimensions—ecological carbon sink,low-carbon maintenance,agricultural carbon reduction and sink enhancement,and urban carbon emission reduction—framed the optimization framework.ND,EP,WC,and ED scenarios provided guidance as the basic reference,optimal benefit,"dual carbon"baseline,and upper development limit,respectively.Additionally,the detailed CSS sub-partitions of MDOS covered most potential scenarios of such ecosystems,demonstrating the applicability of these sub-partitions.These findings provide valuable references for enhancing CSS and hold important significance for low-carbon territorial spatial planning in the MDOS.展开更多
The Kulpawn River Basin(KRB)plays a critical role in supporting rural livelihoods through agriculture,water supply,and biodiversity conservation.However,between 1995 and 2023,significant land use and land cover(LULC)c...The Kulpawn River Basin(KRB)plays a critical role in supporting rural livelihoods through agriculture,water supply,and biodiversity conservation.However,between 1995 and 2023,significant land use and land cover(LULC)changes have been observed,affecting ecosystem services(ESs).This study evaluated the ecosystem service values(ESVs)associated with LULC changes.The random forest algorithm was applied to extract LULC information from Landsat images for 1995,2005,2015,and 2023.The benefit transfer method was employed to estimate the ESVs over the study period.Questionnaires were also used to assess the views of respondents on the drivers of the ES changes in the basin.The results showed that agricultural lands expanded by 14.14%,built-up areas by 15.17%,and light savannah forest by 8.73%,while dense savannah forest and water bodies declined by 25.71%and 20.00%,respectively.The total estimated ESV was 410.09×10^(8),362.92×10^(8),335.30×10^(8),and 319.28×10^(8) USD/(hm^(2)·a)in 1995,2005,2015,and 2023,respectively,indicating that the total ESV declined from 410.09×10^(8) USD/(hm^(2)·a)in 1995 to 319.28×10^(8) USD/(hm^(2)·a)in 2023.The study concludes that the reduction in ESVs is due to the LULC changes resulting from agricultural activities,expansion of built-up areas,population sprawl,and artisanal mining activities.Hence,there is an urgent need to develop programs and strategies to mitigate and curtail the degradation of LULC and ESVs in the basin.These findings reveal a growing ecological vulnerability,threatening water security and rural livelihoods.The study offers valuable insights to guide sustainable land use planning and ecosystem conservation strategies.展开更多
Carbon storage serves as a key indicator of ecosystem services and plays a vital role in maintaining the global carbon balance.Land use and cover change(LUCC)is one of the primary drivers influencing carbon storage va...Carbon storage serves as a key indicator of ecosystem services and plays a vital role in maintaining the global carbon balance.Land use and cover change(LUCC)is one of the primary drivers influencing carbon storage variations in terrestrial ecosystems.Therefore,evaluating the impacts of LUCC on carbon storage is crucial for achieving strategic goals such as the China’s dual carbon goals(including carbon peaking and carbon neutrality).This study focuses on the Aral Irrigation Area in Xinjiang Uygur Autonomous Region,China,to assess the impacts of LUCC on regional carbon storage and their spatiotemporal dynamics.A comprehensive LUCC database from 2000 to 2020 was developed using Landsat satellite imagery and the random forest classification algorithm.The integrated valuation of ecosystem services and trade-offs(InVEST)model was applied to quantify carbon storage and analyze its response to LUCC.Additionally,future LUCC patterns for 2030 were projected under multiple development scenarios using the patch-generating land use simulation(PLUS)model.These future LUCC scenarios were integrated with the InVEST model to simulate carbon storage trends under different land management pathways.Between 2000 and 2020,the dominant land use types in the study area were cropland(area proportion of 35.52%),unused land(34.80%),and orchard land(12.19%).The conversion of unused land and orchard land significantly expanded the area of cropland,which increased by 115,742.55 hm^(2).During this period,total carbon storage and carbon density increased by 7.87×10^(6) Mg C and 20.19 Mg C/hm^(2),respectively.The primary driver of this increase was the conversion of unused land into cropland,accounting for 49.28%of the total carbon storage gain.Carbon storage was notably lower along the northeastern and southeastern edges.By 2030,the projected carbon storage is expected to increase by 0.99×10^(6),1.55×10^(6),and 1.71×10^(6) Mg C under the natural development,cropland protection,and ecological conservation scenarios,respectively.In contrast,under the urban development scenario,carbon storage is projected to decline by 0.40×10^(6) Mg C.In line with China’s dual carbon goals,the ecological conservation scenario emerges as the most effective strategy for enhancing carbon storage.Accordingly,strict enforcement of the cropland red line is recommended.This study provides a valuable scientific foundation for regional ecosystem restoration and sustainable development in arid regions.展开更多
The Liaohe River Basin(LRB)in Northeast China,a critical agricultural and industrial zone,has faced escalating water resource pressures in recent decades due to rapid urbanization,intensified land use changes,and clim...The Liaohe River Basin(LRB)in Northeast China,a critical agricultural and industrial zone,has faced escalating water resource pressures in recent decades due to rapid urbanization,intensified land use changes,and climate variability.Understanding the spatiotemporal dynamics of water yield and its driving factors is essential for sustainable water resource management in this ecologically sensitive region.This study employed the Integrated Valuation of Ecosystem Services and Tradeoffs(InVEST)model to quantify the spatiotemporal patterns of water yield in the LRB(dividing into six sub-basins from east to west:East Liaohe River Basin(ELRB),Taizi River Basin(TRB),Middle Liaohe River Basin(MLRB),West Liaohe River Basin(WLRB),Xinkai River Basin(XRB),and Wulijimuren River Basin(WRB))from 1993 to 2022,with a focus on the impacts of climate change and land use cover change(LUCC).Results revealed that the LRB had an average annual precipitation of 483.15 mm,with an average annual water yield of 247.54 mm,both showing significant upward trend over the 30-a period.Spatially,water yield demonstrated significant heterogeneity,with higher values in southeastern sub-basins and lower values in northwestern sub-basins.The TRB exhibited the highest water yield due to abundant precipitation and favorable topography,while the WRB recorded the lowest water yield owing to arid conditions and sparse vegetation.Precipitation played a significant role in shaping the annual fluctuations and total volume of water yield,with its variability exerting substantially greater impacts than actual evapotranspiration(AET)and LUCC.However,LUCC,particularly cultivated land expansion and grassland reduction,significantly reshaped the spatial distribution of water yield by modifying surface runoff and infiltration patterns.This study provides critical insights into the spatiotemporal dynamics of water yield in the LRB,emphasizing the synergistic effects of climate change and land use change,which are pivotal for optimizing water resource management and advancing regional ecological conservation.展开更多
Accurate and reliable cropland surface information is of vital importance for agricultural planning and food security monitoring. As several global land cover datasets have been independently released, an inter-compar...Accurate and reliable cropland surface information is of vital importance for agricultural planning and food security monitoring. As several global land cover datasets have been independently released, an inter-comparison of these data products on the classification of cropland is highly needed. This paper presents an assessment of cropland classifications in four global land cover datasets, i.e., moderate resolution imaging spectrometer （MODIS） land cover product, global land cover map of 2009 （GlobCover2009）, finer resolution observation and monitoring of global cropland （FROM-GC） and 30-m global land cover dataset （GlobeLand30）. The temporal coverage of these four datasets are circa 2010. One of the typical agricultur- al regions of China, Shaanxi Province, was selected as the study area. The assessment proceeded from three aspects： accuracy, spatial agreement and absolute area. In accuracy assessment, 506 validation samples, which consist of 168 cropland samples and 338 non-cropland ones, were automatically and systematically selected, and manually interpreted by referencing high-resolution images dated from 2009 to 2011 on Google Earth. The results show that the overall accuracy （OA） of four datasets ranges from 61.26 to 80.63%. GlobeLand30 dataset, with the highest accuracy, is the most accurate dataset for cropland classification. The cropland spatial agreement （mainly located in the plain ecotope of Shaanxi） and the non-cropland spatial agreement （sparsely distributed in the south and middle of Shaanxi） of the four datasets only makes up 33.96% of the whole province. FIROM-GC and GlobeLand30, obtaining the highest spatial agreement index of 62.40%, have the highest degree of spatial consistency. In terms of the absolute area, MODIS underestimates the cropland area, while GlobCover2009 significantly overestimates it. These findings are of value in revealing to which extent and on which aspect that these global land cover datasets may agree with each other at small scale on each ecotope region. The approaches taken in this study could be used to derive a fused cropland classification dataset.展开更多
The main objective of this research is to determine the capacity of land cover classification combining spec- tral and textural features of Landsat TM imagery with ancillary geographical data in wetlands of the Sanjia...The main objective of this research is to determine the capacity of land cover classification combining spec- tral and textural features of Landsat TM imagery with ancillary geographical data in wetlands of the Sanjiang Plain, Heilongjiang Province, China. Semi-variograms and Z-test value were calculated to assess the separability of grey-level co-occurrence texture measures to maximize the difference between land cover types. The degree of spatial autocorrelation showed that window sizes of 3×3 pixels and 11×11 pixels were most appropriate for Landsat TM im- age texture calculations. The texture analysis showed that co-occurrence entropy, dissimilarity, and variance texture measures, derived from the Landsat TM spectrum bands and vegetation indices provided the most significant statistical differentiation between land cover types. Subsequently, a Classification and Regression Tree (CART) algorithm was applied to three different combinations of predictors: 1) TM imagery alone (TM-only); 2) TM imagery plus image texture (TM+TXT model); and 3) all predictors including TM imagery, image texture and additional ancillary GIS in- formation (TM+TXT+GIS model). Compared with traditional Maximum Likelihood Classification (MLC) supervised classification, three classification trees predictive models reduced the overall error rate significantly. Image texture measures and ancillary geographical variables depressed the speckle noise effectively and reduced classification error rate of marsh obviously. For classification trees model making use of all available predictors, omission error rate was 12.90% and commission error rate was 10.99% for marsh. The developed method is portable, relatively easy to im- plement and should be applicable in other settings and over larger extents.展开更多
Land cover classification(LCC) in arid regions is of great significance to the assessment, prediction, and management of land desertification. Some studies have shown that the red-edge band of RapidE ye images was eff...Land cover classification(LCC) in arid regions is of great significance to the assessment, prediction, and management of land desertification. Some studies have shown that the red-edge band of RapidE ye images was effective for vegetation identification and could improve LCC accuracy. However, there has been no investigation of the effects of RapidE ye images' red-edge band and vegetation indices on LCC in arid regions where there are spectrally similar land covers mixed with very high or low vegetation coverage information and bare land. This study focused on a typical inland arid desert region located in Dunhuang Basin of northwestern China. First, five feature sets including or excluding the red-edge band and vegetation indices were constructed. Then, a land cover classification system involving plant communities was developed. Finally, random forest algorithm-based models with different feature sets were utilized for LCC. The conclusions drawn were as follows: 1) the red-edge band showed slight contribution to LCC accuracy; 2) vegetation indices had a significant positive effect on LCC; 3) simultaneous addition of the red-edge band and vegetation indices achieved a significant overall accuracy improvement(3.46% from 86.67%). In general, vegetation indices had larger effect than the red-edge band, and simultaneous addition of them significantly increased the accuracy of LCC in arid regions.展开更多
Although the Convolutional Neural Network(CNN)has shown great potential for land cover classification,the frequently used single-scale convolution kernel limits the scope of informa-tion extraction.Therefore,we propos...Although the Convolutional Neural Network(CNN)has shown great potential for land cover classification,the frequently used single-scale convolution kernel limits the scope of informa-tion extraction.Therefore,we propose a Multi-Scale Fully Convolutional Network(MSFCN)with a multi-scale convolutional kernel as well as a Channel Attention Block(CAB)and a Global Pooling Module(GPM)in this paper to exploit discriminative representations from two-dimensional(2D)satellite images.Meanwhile,to explore the ability of the proposed MSFCN for spatio-temporal images,we expand our MSFCN to three-dimension using three-dimensional(3D)CNN,capable of harnessing each land cover category’s time series interac-tion from the reshaped spatio-temporal remote sensing images.To verify the effectiveness of the proposed MSFCN,we conduct experiments on two spatial datasets and two spatio-temporal datasets.The proposed MSFCN achieves 60.366%on the WHDLD dataset and 75.127%on the GID dataset in terms of mIoU index while the figures for two spatio-temporal datasets are 87.753%and 77.156%.Extensive comparative experiments and abla-tion studies demonstrate the effectiveness of the proposed MSFCN.展开更多
High-resolution deep-learning-based remote-sensing imagery analysis has been widely used in land-use and crop-classification mapping. However, the influence of composite feature bands, including complex feature indice...High-resolution deep-learning-based remote-sensing imagery analysis has been widely used in land-use and crop-classification mapping. However, the influence of composite feature bands, including complex feature indices arising from different sensors on the backbone, patch size, and predictions in transferable deep models require further testing. The experiments were conducted in six sites in Henan province from2019 to 2021. This study sought to enable the transfer of classification models across regions and years for Sentinel-2 A(10-m resolution) and Gaofen PMS(2-m resolution) imagery. With feature selection and up-sampling of small samples, the performance of UNet++ architecture on five backbones and four patch sizes was examined. Joint loss, mean Intersection over Union(m Io U), and epoch time were analyzed, and the optimal backbone and patch size for both sensors were Timm-Reg Net Y-320 and 256 × 256, respectively. The overall accuracy and Fscores of the Sentinel-2 A predictions ranged from 96.86% to 97.72%and 71.29% to 80.75%, respectively, compared to 75.34%–97.72% and 54.89%–73.25% for the Gaofen predictions. The accuracies of each site indicated that patch size exerted a greater influence on model performance than the backbone. The feature-selection-based predictions with UNet++ architecture and upsampling of minor classes demonstrated the capabilities of deep-learning generalization for classifying complex ground objects, offering improved performance compared to the UNet, Deeplab V3+, Random Forest, and Object-Oriented Classification models. In addition to the overall accuracy, confusion matrices,precision, recall, and F1 scores should be evaluated for minor land-cover types. This study contributes to large-scale, dynamic, and near-real-time land-use and crop mapping by integrating deep learning and multi-source remote-sensing imagery.展开更多
Land cover classification is the core of converting satellite imagery to available geographic data.However,spectral signatures do not always provide enough information in classification decisions.Thus,the application ...Land cover classification is the core of converting satellite imagery to available geographic data.However,spectral signatures do not always provide enough information in classification decisions.Thus,the application of multi-source data becomes necessary.This paper presents an evidential reasoning (ER) approach to incorporate Landsat TM imagery,altitude and slope data.Results show that multi-source data contribute to the classification accuracy achieved by the ER method,whereas play a negative role to that derived by maximum likelihood classifier (MLC).In comparison to the results derived based on TM imagery alone,the overall accuracy rate of the ER method increases by 7.66% and that of the MLC method decreases by 8.35% when all data sources (TM plus altitude and slope) are accessible.The ER method is regarded as a better approach for multi-source image classification.In addition,the method produces not only an accurate classification result,but also the uncertainty which presents the inherent difficulty in classification decisions.The uncertainty associated to the ER classification image is evaluated and proved to be useful for improved classification accuracy.展开更多
This paper extends recent research into the usefulness of volunteered photos for land cover extraction,and investigates whether this usefulness can be automatically assessed by an easily accessible,off-the-shelf neura...This paper extends recent research into the usefulness of volunteered photos for land cover extraction,and investigates whether this usefulness can be automatically assessed by an easily accessible,off-the-shelf neural network pre-trained on a variety of scene characteristics.Geotagged photographs are sometimes presented to volunteers as part of a game which requires them to extract relevant facts about land use.The challenge is to select the most relevant photographs in order to most efficiently extract the useful information while maintaining the engagement and interests of volunteers.By repurposing an existing network which had been trained on an extensive library of potentially relevant features,we can quickly carry out initial assessments of the general value of this approach,pick out especially salient features,and identify focus areas for future neural network training and development.We compare two approaches to extract land cover information from the network:a simple post hoc weighting approach accessible to non-technical audiences and a more complex decision tree approach that involves training on domain-specific features of interest.Both approaches had reasonable success in characterizing human influence within a scene when identifying the land use types(as classified by Urban Atlas)present within a buffer around the photograph’s location.This work identifies important limitations and opportunities for using volunteered photographs as follows:(1)the false precision of a photograph’s location is less useful for identifying on-the-spot land cover than the information it can give on neighbouring combinations of land cover;(2)groundacquired photographs,interpreted by a neural network,can supplement plan view imagery by identifying features which will never be discernible from above;(3)when dealing with contexts where there are very few exemplars of particular classes,an independent a posteriori weighting of existing scene attributes and categories can buffer against over-specificity.展开更多
This study focused on land cover mapping based on synthetic images,especially using the method of spatial and temporal classification as well as the accuracy validation of their results.Our experimental results indica...This study focused on land cover mapping based on synthetic images,especially using the method of spatial and temporal classification as well as the accuracy validation of their results.Our experimental results indicate that the accuracy of land cover map based on synthetic imagery and actual observation has a similar standard compared with actual land cover survey data.These findings facilitate land cover mapping with synthetic data in the area where actual observation is missing.Furthermore,in order to improve the quality of the land cover mapping,this research employed the spatial and temporal Markov random field classification approach.Test results show that overall mapping accuracy can be increased by approximately 5% after applying spatial and temporal classification.This finding contributes towards the achievement of higher quality land cover mapping of areas with missing data by using spatial and temporal information.展开更多
Using an unmanned aerial vehicle (UAV) paired with image semantic segmentation to classify land cover within natural vegetation can promote the development of forest and grassland field. Semantic segmentation normally...Using an unmanned aerial vehicle (UAV) paired with image semantic segmentation to classify land cover within natural vegetation can promote the development of forest and grassland field. Semantic segmentation normally excels in medical and building classification, but its usefulness in mixed forest-grassland ecosystems in semi-arid to semi-humid climates is unknown. This study proposes a new semantic segmentation network of LResU-net in which residual convolution unit (RCU) and loop convolution unit (LCU) are added to the U-net framework to classify images of different land covers generated by UAV high resolution. The selected model enhanced classification accuracy by increasing gradient mapping via RCU and modifying the size of convolution layers via LCU as well as reducing convolution kernels. To achieve this objective, a group of orthophotos were taken at an altitude of 260 m for testing in a natural forest-grassland ecosystem of Keyouqianqi, Inner Mongolia, China, and compared the results with those of three other network models (U-net, ResU-net and LU-net). The results show that both the highest kappa coefficient (0.86) and the highest overall accuracy (93.7%) resulted from LResU-net, and the value of most land covers provided by the producer’s and user’s accuracy generated in LResU-net exceeded 0.85. The pixel-area ratio approach was used to calculate the real areas of 10 different land covers where grasslands were 67.3%. The analysis of the effect of RCU and LCU on the model training performance indicates that the time of each epoch was shortened from U-net (358 s) to LResU-net (282 s). In addition, in order to classify areas that are not distinguishable, unclassified areas were defined and their impact on classification. LResU-net generated significantly more accurate results than the other three models and was regarded as the most appropriate approach to classify land cover in mixed forest-grassland ecosystems.展开更多
文摘Detailed analysis of Land Use/Land Cover （LULC） using remote sensing data in complex irrigated basins provides complete profile for better water resource management and planning. Using remote sensing data, this study provides detailed land use maps of the Lower Chenab Canal irrigated region of Pakistan from 2005 to 2012 for LULC change detection. Major crop types are demarcated by identifying temporal profiles of NDVI using MODIS 250 m × 250 m spatial resolution data. Wheat and rice are found to be major crops in rabi and kharif seasons, respectively. Accuracy assessment of prepared maps is performed using three dif- ferent techniques： error matrix approach, comparison with ancillary data and with previous study. Producer and user accuracies for each class are calculated along with kappa coeffi- cients （K）. The average overall accuracies for rabi and kharif are 82.83% and 78.21%, re- spectively. Producer and user accuracies for individual class range respectively between 72.5% to 77% and 70.1% to 84.3% for rabi and 76.6% to 90.2% and 72% to 84.7% for kharif. The K values range between 0.66 to 0.77 for rabi with average of 0.73, and from 0.69 to 0.74 with average of 0.71 for kharif. LULC change detection indicates that wheat and rice have less volatility of change in comparison with both rabi and kharif fodders. Transformation be- tween cotton and rice is less common due to their completely different cropping conditions. Results of spatial and temporal LULC distributions and their seasonal variations provide useful insights for establishing realistic LULC scenarios for hydrological studies.
文摘Remote sensing is one of the tool which is very important for the production of Land use and land cover maps through a process called image classification. For the image classification process to be successfully, several factors should be considered including availability of quality Landsat imagery and secondary data, a precise classification process and user’s experiences and expertise of the procedures. The objective of this research was to classify and map land-use/land-cover of the study area using remote sensing and Geospatial Information System (GIS) techniques. This research includes two sections (1) Landuse/Landcover (LULC) classification and (2) accuracy assessment. In this study supervised classification was performed using Non Parametric Rule. The major LULC classified were agriculture (65.0%), water body (4.0%), and built up areas (18.3%), mixed forest (5.2%), shrubs (7.0%), and Barren/bare land (0.5%). The study had an overall classification accuracy of 81.7% and kappa coefficient (K) of 0.722. The kappa coefficient is rated as substantial and hence the classified image found to be fit for further research. This study present essential source of information whereby planners and decision makers can use to sustainably plan the environment.
基金supported by the Deanship of Research and Graduate Studies at the King Khalid University(RGP2/287/46)the Princess Nourah bint Abdulrahman University Researchers Supporting Project(PNURSP2025R733)+1 种基金the Princess Nourah bint Abdulrahman University Research Supporting Project(RSPD2025R787)the King Saud University,Saudi Arabia.
文摘Challenges in land use and land cover(LULC)include rapid urbanization encroaching on agricultural land,leading to fragmentation and loss of natural habitats.However,the effects of urbanization on LULC of different crop types are less concerned.The study assessed the impacts of LULC changes on agriculture and drought vulnerability in the Aguascalientes region,Mexico,from 1994 to 2024,and predicted the LULC in 2034 using remote sensing data,with the goals of sustainable land management and climate resilience strategies.Despite increasing urbanization and drought,the integration of satellite imagery and machine learning models in LULC analysis has been underutilized in this region.Using Landsat imagery,we assessed crop attributes through indices such as normalized difference vegetation index(NDVI),normalized difference water index(NDWI),normalized difference moisture index(NDMI),and vegetation condition index(VCI),alongside watershed delineation and spectral features.The random forest model was applied to classify LULC,providing insights into both historical and future trends.Results indicated a significant decline in vegetation cover(109.13 km^(2))from 1994 to 2024,accompanied by an increase in built-up land(75.11 km^(2))and bare land(67.13 km^(2)).Projections suggested a further decline in vegetation cover(41.51 km^(2))and continued urban land expansion by 2034.The study found that paddy crops exhibited the highest values,while common bean and maize performed poorly.Drought analysis revealed that mildly dry areas in 2004 became severely dry in 2024,highlighting the increasing vulnerability of agriculture to climate change.The study concludes that sustainable land management,improved water resource practices,and advanced monitoring techniques are essential to mitigate the adverse effects of LULC changes on agricultural productivity and drought resilience in the area.These findings contribute to the understanding of how remote sensing can be effectively used for long-term agricultural planning and environmental sustainability.
文摘Cloud cover constitutes a major obstacle to land cover classification in the humid tropical regions when using optical remote sensing such as Landsat imagery. The advent of freely available Sentinel-1 C band synthetic aperture radar (SAR) imagery offers new opportunities for land cover classification in frequently cloud covered environments. In this study, we investigated the utility of Sentinel-1 for extracting land use land cover (LULC) information in the coastal low lying strip of Douala, Cameroon when compared with Landsat enhanced thematic mapper (TM). We also assessed the potential of integrating Sentinel-1 and Landsat. The major LULC classes in the region included water, settlement, bare ground, dark mangroves, green mangroves, swampy vegetation, rubber, coastal forest and other vegetation and palms. Textural variables including mean, correlation, contrast and entropy were derived from the Sentinel-1 C band. Various conventional image processing techniques and the support vector machine (SVM) algorithm were applied. Only four land cover classes (settlement, water, mangroves and other vegetation and rubber) could be calibrated and validated using SAR imagery due to speckles. The Sentinel-1 only classification yielded a lower overall classification accuracy (67.65% when compared to all Landsat bands (88.7%)). The integrated Sentinel-1 and Landsat data showed no significant differences in overall accuracy assessment (88.71% and 88.59%, respectively). The three best spectral bands (5, 6, 7) of Landsat imagery yielded the highest overall accuracy assessment (91.96%). in the study. These results demonstrate a lower potential of Sentinel-1 for land cover classification in the Douala estuary when compared with cloud free Landsat images. However, comparable results were obtained when only broad classes were considered.
基金supported by the National Natural Science Foundation of China[grant number 41930104]by the Research Grants Council of Hong Kong[grant number PolyU 152219/18E].
文摘Information on Land Use and Land Cover Map(LULCM)is essential for environment and socioeconomic applications.Such maps are generally derived from Multispectral Remote Sensing Images(MRSI)via classification.The classification process can be described as information flow from images to maps through a trained classifier.Characterizing the information flow is essential for understanding the classification mechanism,providing solutions that address such theoretical issues as“what is the maximum number of classes that can be classified from a given MRSI?”and“how much information gain can be obtained?”Consequently,two interesting questions naturally arise,i.e.(i)How can we characterize the information flow?and(ii)What is the mathematical form of the information flow?To answer these two questions,this study first hypothesizes that thermodynamic entropy is the appropriate measure of information for both MRSI and LULCM.This hypothesis is then supported by kinetic-theory-based experiments.Thereafter,upon such an entropy,a generalized Jarzynski equation is formulated to mathematically model the information flow,which contains such parameters as thermodynamic entropy of MRSI,thermodynamic entropy of LULCM,weighted F1-score(classification accuracy),and total number of classes.This generalized Jarzynski equation has been successfully validated by hypothesis-driven experiments where 694 Sentinel-2 images are classified into 10 classes by four classical classifiers.This study provides a way for linking thermodynamic laws and concepts to the characterization and understanding of information flow in land cover classification,opening a new door for constructing domain knowledge.
文摘Human well-being and livelihoods depend on natural ecosystem services(ESs).Following the increment of population,ESs have been deteriorated over time.Ultimately,land use/land cover(LULC)changes have a profound impact on the change of ecosystem.The primary goal of this study is to determine the impacts of LULC changes on ecosystem service values(ESVs)in the upper Gilgel Abbay watershed,Ethiopia.Changes in LULC types were studied using three Landsat images representing 1986,2003,and 2021.The Landsat images were classified using a supervised image classification technique in Earth Resources Data Analysis System(ERDAS)Imagine 2014.We classified ESs in this study into four categories(including provisioning,regulating,supporting,and cultural services)based on global ES classification scheme.The adjusted ESV coefficient benefit approach was employed to measure the impacts of LULC changes on ESVs.Five LULC types were identified in this study,including cultivated land,forest,shrubland,grassland,and water body.The result revealed that the area of cultivated land accounted for 64.50%,71.50%,and 61.50%of the total area in 1986,2003,and 2021,respectively.The percentage of the total area covered by forest was 9.50%,5.90%,and 14.80%in 1986,2003,and 2021,respectively.Result revealed that the total ESV decreased from 7.42×10^(7) to 6.44×10^(7) USD between 1986 and 2003.This is due to the expansion of cultivated land at the expense of forest and shrubland.However,the total ESV increased from 6.44×10^(7) to 7.76×10^(7) USD during 2003-2021,because of the increment of forest and shrubland.The expansion of cultivated land and the reductions of forest and shrubland reduced most individual ESs during 1986-2003.Nevertheless,the increase in forest and shrubland at the expense of cultivated land enhanced many ESs during 2003-2021.Therefore,the findings suggest that appropriate land use practices should be scaled-up to sustainably maintain ESs.
基金funded by the European Commission,CINEA Horizon Europe project no.101081307“Towards Sustainable Land-Use in the Context of Climate Change and Biodiversity in Europe(Europe-LAND)”。
文摘Chalet farming,as a specific type of agricultural landscape management,has been established in many European mountain ranges,including the Krkono?e Mountains and the Hruby Jeseník Mountains in Czechia.During the operation of such farming from 16/17th century till 1945,many changes in land use/land cover and landscape at all occurred,which are generally evaluated positively.Turbulent events including political,economic and social changes and the displacement of the German-speaking population associated with them in the mid-20th century rapidly ended this development,causing significant landscape changes,such as the abandonment of agricultural land and succession,afforestation,expansion of the alpine tree line,reduction of diversity.The aim of our study is to evaluate changes of land cover(forests,dwarf pine,grasslands,other areas)from 1936/1946 till 2021,secondary succession and driving forces of change for selected meadow enclaves in the Krkonose Mountains and the Hruby Jeseník Mountains after the decline of mountain chalet farming since the middle of 20th century.We used remote sensing methods(aerial imagery)and field research(dendrochronology and comparative photography)to detect the land use/land cover changes in the selected study areas in the Krkono?e Mountains and the Hruby Jeseník Mountains.We documented the process of the succession,which occurred almost immediately after the end of farming,peaking about 10–20 years later,with an earlier start in the Hruby Jeseník Mountains.The succession led to the significant change of land use/land cover and these processes were similar in both mountain ranges.The largest changes were a decrease in grasslands by 62%–64%and an increase in forest area by 33%–40%for both study areas.The abandonment of land is the main consequence of a crucial political driving forces(displacement of German-speaking population)in the Krkono?e Mountains and the Hruby Jeseník Mountains.
基金funded by the Gansu Provincial Department of Education's University Teacher Innovation Fund Project(2025A-001)the Gansu Provincial Philosophy and Social Science Planning Project(2024YB088).
文摘Optimizing the spatial pattern of carbon sequestration service is essential for advancing regional low-carbon development,accelerating the achievement of the"dual carbon"goals,and promoting the high-quality development of ecological environment.The carbon sequestration capacity within the mountain-desert-oasis system(MDOS),a unique landscape pattern,exhibits significant gradient characteristics,and its carbon sink potential can be substantially improved through multi-scale spatial optimization.This study employed the Integrated Valuation of Ecosystem Services and Tradeoff(InVEST)model to estimate carbon storage and sequestration(CSS)in the Gansu section of Heihe River Basin,China,a representative MDOS,based on land use/land cover(LULC)data from 1990 to 2020.The Patch-level Land Use Simulation(PLUS)model was coupled to simulate LULC and estimate carrying CSS under natural development(ND),ecological protection(EP),water constraint(WC),and economic development(ED)scenarios for 2035.Furthermore,the study constructed and optimized the CSS pattern on the basis of economic and ecological benefits,exploring the guiding significance of different scenarios for pattern optimization.The results showed that CSS spatial distribution is closely correlated with LULC pattern,and CSS is expected to improve in the future.CSS showed an overall increase across subsystems during 1990–2020,but varied across LULC types.CSS of construction land in all subsystems exhibited an increasing trend,while CSS of unused land showed a decreasing trend,with specific changes of 1.68×103 and 3.43×105 t,respectively.Regional CSS dynamics were mainly driven by conversions among unused land,cultivated land,and grassland.The CSS pattern of MDOS was divided into carbon sink functional region(CSFR),low carbon conservation region(LCCR),low carbon economic region(LCER),and economic development region(EDR).Water resources coordination served as the basis of pattern optimization,while the four dimensions—ecological carbon sink,low-carbon maintenance,agricultural carbon reduction and sink enhancement,and urban carbon emission reduction—framed the optimization framework.ND,EP,WC,and ED scenarios provided guidance as the basic reference,optimal benefit,"dual carbon"baseline,and upper development limit,respectively.Additionally,the detailed CSS sub-partitions of MDOS covered most potential scenarios of such ecosystems,demonstrating the applicability of these sub-partitions.These findings provide valuable references for enhancing CSS and hold important significance for low-carbon territorial spatial planning in the MDOS.
基金financial assistance from the European Union(Contract number:AFS2023/444-387)。
文摘The Kulpawn River Basin(KRB)plays a critical role in supporting rural livelihoods through agriculture,water supply,and biodiversity conservation.However,between 1995 and 2023,significant land use and land cover(LULC)changes have been observed,affecting ecosystem services(ESs).This study evaluated the ecosystem service values(ESVs)associated with LULC changes.The random forest algorithm was applied to extract LULC information from Landsat images for 1995,2005,2015,and 2023.The benefit transfer method was employed to estimate the ESVs over the study period.Questionnaires were also used to assess the views of respondents on the drivers of the ES changes in the basin.The results showed that agricultural lands expanded by 14.14%,built-up areas by 15.17%,and light savannah forest by 8.73%,while dense savannah forest and water bodies declined by 25.71%and 20.00%,respectively.The total estimated ESV was 410.09×10^(8),362.92×10^(8),335.30×10^(8),and 319.28×10^(8) USD/(hm^(2)·a)in 1995,2005,2015,and 2023,respectively,indicating that the total ESV declined from 410.09×10^(8) USD/(hm^(2)·a)in 1995 to 319.28×10^(8) USD/(hm^(2)·a)in 2023.The study concludes that the reduction in ESVs is due to the LULC changes resulting from agricultural activities,expansion of built-up areas,population sprawl,and artisanal mining activities.Hence,there is an urgent need to develop programs and strategies to mitigate and curtail the degradation of LULC and ESVs in the basin.These findings reveal a growing ecological vulnerability,threatening water security and rural livelihoods.The study offers valuable insights to guide sustainable land use planning and ecosystem conservation strategies.
基金supported by the National Key R&D Program of China(2022YFD1900503).
文摘Carbon storage serves as a key indicator of ecosystem services and plays a vital role in maintaining the global carbon balance.Land use and cover change(LUCC)is one of the primary drivers influencing carbon storage variations in terrestrial ecosystems.Therefore,evaluating the impacts of LUCC on carbon storage is crucial for achieving strategic goals such as the China’s dual carbon goals(including carbon peaking and carbon neutrality).This study focuses on the Aral Irrigation Area in Xinjiang Uygur Autonomous Region,China,to assess the impacts of LUCC on regional carbon storage and their spatiotemporal dynamics.A comprehensive LUCC database from 2000 to 2020 was developed using Landsat satellite imagery and the random forest classification algorithm.The integrated valuation of ecosystem services and trade-offs(InVEST)model was applied to quantify carbon storage and analyze its response to LUCC.Additionally,future LUCC patterns for 2030 were projected under multiple development scenarios using the patch-generating land use simulation(PLUS)model.These future LUCC scenarios were integrated with the InVEST model to simulate carbon storage trends under different land management pathways.Between 2000 and 2020,the dominant land use types in the study area were cropland(area proportion of 35.52%),unused land(34.80%),and orchard land(12.19%).The conversion of unused land and orchard land significantly expanded the area of cropland,which increased by 115,742.55 hm^(2).During this period,total carbon storage and carbon density increased by 7.87×10^(6) Mg C and 20.19 Mg C/hm^(2),respectively.The primary driver of this increase was the conversion of unused land into cropland,accounting for 49.28%of the total carbon storage gain.Carbon storage was notably lower along the northeastern and southeastern edges.By 2030,the projected carbon storage is expected to increase by 0.99×10^(6),1.55×10^(6),and 1.71×10^(6) Mg C under the natural development,cropland protection,and ecological conservation scenarios,respectively.In contrast,under the urban development scenario,carbon storage is projected to decline by 0.40×10^(6) Mg C.In line with China’s dual carbon goals,the ecological conservation scenario emerges as the most effective strategy for enhancing carbon storage.Accordingly,strict enforcement of the cropland red line is recommended.This study provides a valuable scientific foundation for regional ecosystem restoration and sustainable development in arid regions.
基金funded by the Liaoning Provincial Social Science Planning Fund(L22AYJ010).
文摘The Liaohe River Basin(LRB)in Northeast China,a critical agricultural and industrial zone,has faced escalating water resource pressures in recent decades due to rapid urbanization,intensified land use changes,and climate variability.Understanding the spatiotemporal dynamics of water yield and its driving factors is essential for sustainable water resource management in this ecologically sensitive region.This study employed the Integrated Valuation of Ecosystem Services and Tradeoffs(InVEST)model to quantify the spatiotemporal patterns of water yield in the LRB(dividing into six sub-basins from east to west:East Liaohe River Basin(ELRB),Taizi River Basin(TRB),Middle Liaohe River Basin(MLRB),West Liaohe River Basin(WLRB),Xinkai River Basin(XRB),and Wulijimuren River Basin(WRB))from 1993 to 2022,with a focus on the impacts of climate change and land use cover change(LUCC).Results revealed that the LRB had an average annual precipitation of 483.15 mm,with an average annual water yield of 247.54 mm,both showing significant upward trend over the 30-a period.Spatially,water yield demonstrated significant heterogeneity,with higher values in southeastern sub-basins and lower values in northwestern sub-basins.The TRB exhibited the highest water yield due to abundant precipitation and favorable topography,while the WRB recorded the lowest water yield owing to arid conditions and sparse vegetation.Precipitation played a significant role in shaping the annual fluctuations and total volume of water yield,with its variability exerting substantially greater impacts than actual evapotranspiration(AET)and LUCC.However,LUCC,particularly cultivated land expansion and grassland reduction,significantly reshaped the spatial distribution of water yield by modifying surface runoff and infiltration patterns.This study provides critical insights into the spatiotemporal dynamics of water yield in the LRB,emphasizing the synergistic effects of climate change and land use change,which are pivotal for optimizing water resource management and advancing regional ecological conservation.
基金supported by the National High-Tech R&D Program of China (2012AA12A408)the Independent Scientific Research of Tsinghua University,China (20131089277,553302001)
文摘Accurate and reliable cropland surface information is of vital importance for agricultural planning and food security monitoring. As several global land cover datasets have been independently released, an inter-comparison of these data products on the classification of cropland is highly needed. This paper presents an assessment of cropland classifications in four global land cover datasets, i.e., moderate resolution imaging spectrometer （MODIS） land cover product, global land cover map of 2009 （GlobCover2009）, finer resolution observation and monitoring of global cropland （FROM-GC） and 30-m global land cover dataset （GlobeLand30）. The temporal coverage of these four datasets are circa 2010. One of the typical agricultur- al regions of China, Shaanxi Province, was selected as the study area. The assessment proceeded from three aspects： accuracy, spatial agreement and absolute area. In accuracy assessment, 506 validation samples, which consist of 168 cropland samples and 338 non-cropland ones, were automatically and systematically selected, and manually interpreted by referencing high-resolution images dated from 2009 to 2011 on Google Earth. The results show that the overall accuracy （OA） of four datasets ranges from 61.26 to 80.63%. GlobeLand30 dataset, with the highest accuracy, is the most accurate dataset for cropland classification. The cropland spatial agreement （mainly located in the plain ecotope of Shaanxi） and the non-cropland spatial agreement （sparsely distributed in the south and middle of Shaanxi） of the four datasets only makes up 33.96% of the whole province. FIROM-GC and GlobeLand30, obtaining the highest spatial agreement index of 62.40%, have the highest degree of spatial consistency. In terms of the absolute area, MODIS underestimates the cropland area, while GlobCover2009 significantly overestimates it. These findings are of value in revealing to which extent and on which aspect that these global land cover datasets may agree with each other at small scale on each ecotope region. The approaches taken in this study could be used to derive a fused cropland classification dataset.
基金Under the auspices of National Natural Science Foundation of China (No. 40871188) National Key Technologies R&D Program of China (No. 2006BAD23B03)
文摘The main objective of this research is to determine the capacity of land cover classification combining spec- tral and textural features of Landsat TM imagery with ancillary geographical data in wetlands of the Sanjiang Plain, Heilongjiang Province, China. Semi-variograms and Z-test value were calculated to assess the separability of grey-level co-occurrence texture measures to maximize the difference between land cover types. The degree of spatial autocorrelation showed that window sizes of 3×3 pixels and 11×11 pixels were most appropriate for Landsat TM im- age texture calculations. The texture analysis showed that co-occurrence entropy, dissimilarity, and variance texture measures, derived from the Landsat TM spectrum bands and vegetation indices provided the most significant statistical differentiation between land cover types. Subsequently, a Classification and Regression Tree (CART) algorithm was applied to three different combinations of predictors: 1) TM imagery alone (TM-only); 2) TM imagery plus image texture (TM+TXT model); and 3) all predictors including TM imagery, image texture and additional ancillary GIS in- formation (TM+TXT+GIS model). Compared with traditional Maximum Likelihood Classification (MLC) supervised classification, three classification trees predictive models reduced the overall error rate significantly. Image texture measures and ancillary geographical variables depressed the speckle noise effectively and reduced classification error rate of marsh obviously. For classification trees model making use of all available predictors, omission error rate was 12.90% and commission error rate was 10.99% for marsh. The developed method is portable, relatively easy to im- plement and should be applicable in other settings and over larger extents.
基金Under the auspices of Fundamental Research Funds for Central Universities,China University of Geosciences(Wuhan)(No.CUGL150417)National Natural Science Foundation of China(No.41274036,41301026)
文摘Land cover classification(LCC) in arid regions is of great significance to the assessment, prediction, and management of land desertification. Some studies have shown that the red-edge band of RapidE ye images was effective for vegetation identification and could improve LCC accuracy. However, there has been no investigation of the effects of RapidE ye images' red-edge band and vegetation indices on LCC in arid regions where there are spectrally similar land covers mixed with very high or low vegetation coverage information and bare land. This study focused on a typical inland arid desert region located in Dunhuang Basin of northwestern China. First, five feature sets including or excluding the red-edge band and vegetation indices were constructed. Then, a land cover classification system involving plant communities was developed. Finally, random forest algorithm-based models with different feature sets were utilized for LCC. The conclusions drawn were as follows: 1) the red-edge band showed slight contribution to LCC accuracy; 2) vegetation indices had a significant positive effect on LCC; 3) simultaneous addition of the red-edge band and vegetation indices achieved a significant overall accuracy improvement(3.46% from 86.67%). In general, vegetation indices had larger effect than the red-edge band, and simultaneous addition of them significantly increased the accuracy of LCC in arid regions.
基金supported by the National Natural Science Foundation of China[grant number 41671452].
文摘Although the Convolutional Neural Network(CNN)has shown great potential for land cover classification,the frequently used single-scale convolution kernel limits the scope of informa-tion extraction.Therefore,we propose a Multi-Scale Fully Convolutional Network(MSFCN)with a multi-scale convolutional kernel as well as a Channel Attention Block(CAB)and a Global Pooling Module(GPM)in this paper to exploit discriminative representations from two-dimensional(2D)satellite images.Meanwhile,to explore the ability of the proposed MSFCN for spatio-temporal images,we expand our MSFCN to three-dimension using three-dimensional(3D)CNN,capable of harnessing each land cover category’s time series interac-tion from the reshaped spatio-temporal remote sensing images.To verify the effectiveness of the proposed MSFCN,we conduct experiments on two spatial datasets and two spatio-temporal datasets.The proposed MSFCN achieves 60.366%on the WHDLD dataset and 75.127%on the GID dataset in terms of mIoU index while the figures for two spatio-temporal datasets are 87.753%and 77.156%.Extensive comparative experiments and abla-tion studies demonstrate the effectiveness of the proposed MSFCN.
基金supported by the National Science and Technology Platform Construction (2005DKA32300)the Major Research Projects of the Ministry of Education (16JJD770019)the Open Program of Collaborative Innovation Center of Geo-Information Technology for Smart Central Plains Henan Province (G202006)。
文摘High-resolution deep-learning-based remote-sensing imagery analysis has been widely used in land-use and crop-classification mapping. However, the influence of composite feature bands, including complex feature indices arising from different sensors on the backbone, patch size, and predictions in transferable deep models require further testing. The experiments were conducted in six sites in Henan province from2019 to 2021. This study sought to enable the transfer of classification models across regions and years for Sentinel-2 A(10-m resolution) and Gaofen PMS(2-m resolution) imagery. With feature selection and up-sampling of small samples, the performance of UNet++ architecture on five backbones and four patch sizes was examined. Joint loss, mean Intersection over Union(m Io U), and epoch time were analyzed, and the optimal backbone and patch size for both sensors were Timm-Reg Net Y-320 and 256 × 256, respectively. The overall accuracy and Fscores of the Sentinel-2 A predictions ranged from 96.86% to 97.72%and 71.29% to 80.75%, respectively, compared to 75.34%–97.72% and 54.89%–73.25% for the Gaofen predictions. The accuracies of each site indicated that patch size exerted a greater influence on model performance than the backbone. The feature-selection-based predictions with UNet++ architecture and upsampling of minor classes demonstrated the capabilities of deep-learning generalization for classifying complex ground objects, offering improved performance compared to the UNet, Deeplab V3+, Random Forest, and Object-Oriented Classification models. In addition to the overall accuracy, confusion matrices,precision, recall, and F1 scores should be evaluated for minor land-cover types. This study contributes to large-scale, dynamic, and near-real-time land-use and crop mapping by integrating deep learning and multi-source remote-sensing imagery.
基金Under the auspices of National Natural Science Foundation of China (No.40871188)Knowledge Innovation Programs of Chinese Academy of Sciences (No.INFO-115-C01-SDB4-05)
文摘Land cover classification is the core of converting satellite imagery to available geographic data.However,spectral signatures do not always provide enough information in classification decisions.Thus,the application of multi-source data becomes necessary.This paper presents an evidential reasoning (ER) approach to incorporate Landsat TM imagery,altitude and slope data.Results show that multi-source data contribute to the classification accuracy achieved by the ER method,whereas play a negative role to that derived by maximum likelihood classifier (MLC).In comparison to the results derived based on TM imagery alone,the overall accuracy rate of the ER method increases by 7.66% and that of the MLC method decreases by 8.35% when all data sources (TM plus altitude and slope) are accessible.The ER method is regarded as a better approach for multi-source image classification.In addition,the method produces not only an accurate classification result,but also the uncertainty which presents the inherent difficulty in classification decisions.The uncertainty associated to the ER classification image is evaluated and proved to be useful for improved classification accuracy.
基金supported by the COST Action[grant number TD1202]‘Mapping and the Citizen Sensor’.
文摘This paper extends recent research into the usefulness of volunteered photos for land cover extraction,and investigates whether this usefulness can be automatically assessed by an easily accessible,off-the-shelf neural network pre-trained on a variety of scene characteristics.Geotagged photographs are sometimes presented to volunteers as part of a game which requires them to extract relevant facts about land use.The challenge is to select the most relevant photographs in order to most efficiently extract the useful information while maintaining the engagement and interests of volunteers.By repurposing an existing network which had been trained on an extensive library of potentially relevant features,we can quickly carry out initial assessments of the general value of this approach,pick out especially salient features,and identify focus areas for future neural network training and development.We compare two approaches to extract land cover information from the network:a simple post hoc weighting approach accessible to non-technical audiences and a more complex decision tree approach that involves training on domain-specific features of interest.Both approaches had reasonable success in characterizing human influence within a scene when identifying the land use types(as classified by Urban Atlas)present within a buffer around the photograph’s location.This work identifies important limitations and opportunities for using volunteered photographs as follows:(1)the false precision of a photograph’s location is less useful for identifying on-the-spot land cover than the information it can give on neighbouring combinations of land cover;(2)groundacquired photographs,interpreted by a neural network,can supplement plan view imagery by identifying features which will never be discernible from above;(3)when dealing with contexts where there are very few exemplars of particular classes,an independent a posteriori weighting of existing scene attributes and categories can buffer against over-specificity.
基金supported in part by the National High-Tech R&D Program(863 program)under grant number 2009AA122004the National Natural Science Foundation of China under grant number 60171009the Hong Kong Research Grant Council under grant number CUHK 444612.
文摘This study focused on land cover mapping based on synthetic images,especially using the method of spatial and temporal classification as well as the accuracy validation of their results.Our experimental results indicate that the accuracy of land cover map based on synthetic imagery and actual observation has a similar standard compared with actual land cover survey data.These findings facilitate land cover mapping with synthetic data in the area where actual observation is missing.Furthermore,in order to improve the quality of the land cover mapping,this research employed the spatial and temporal Markov random field classification approach.Test results show that overall mapping accuracy can be increased by approximately 5% after applying spatial and temporal classification.This finding contributes towards the achievement of higher quality land cover mapping of areas with missing data by using spatial and temporal information.
基金The work was supported by the Fundamental Research Funds for the Central Universities(NO.2021ZY92)major program of State Administration of Forestry and Grassland“Study on the assessment technologies for ecologically restoring the degraded grasslands”(20,200,507).
文摘Using an unmanned aerial vehicle (UAV) paired with image semantic segmentation to classify land cover within natural vegetation can promote the development of forest and grassland field. Semantic segmentation normally excels in medical and building classification, but its usefulness in mixed forest-grassland ecosystems in semi-arid to semi-humid climates is unknown. This study proposes a new semantic segmentation network of LResU-net in which residual convolution unit (RCU) and loop convolution unit (LCU) are added to the U-net framework to classify images of different land covers generated by UAV high resolution. The selected model enhanced classification accuracy by increasing gradient mapping via RCU and modifying the size of convolution layers via LCU as well as reducing convolution kernels. To achieve this objective, a group of orthophotos were taken at an altitude of 260 m for testing in a natural forest-grassland ecosystem of Keyouqianqi, Inner Mongolia, China, and compared the results with those of three other network models (U-net, ResU-net and LU-net). The results show that both the highest kappa coefficient (0.86) and the highest overall accuracy (93.7%) resulted from LResU-net, and the value of most land covers provided by the producer’s and user’s accuracy generated in LResU-net exceeded 0.85. The pixel-area ratio approach was used to calculate the real areas of 10 different land covers where grasslands were 67.3%. The analysis of the effect of RCU and LCU on the model training performance indicates that the time of each epoch was shortened from U-net (358 s) to LResU-net (282 s). In addition, in order to classify areas that are not distinguishable, unclassified areas were defined and their impact on classification. LResU-net generated significantly more accurate results than the other three models and was regarded as the most appropriate approach to classify land cover in mixed forest-grassland ecosystems.
